Managed Service for Apache Spark MCP server
Google's hosted MCP server for Managed Service for Apache Spark (formerly Dataproc). An assistant connects over Streamable HTTP and authenticates with OAuth 2.0 under IAM; API keys are not accepted.
What it does
Google's hosted MCP server for Managed Service for Apache Spark (formerly Dataproc). An assistant connects over Streamable HTTP and authenticates with OAuth 2.0 under IAM; API keys are not accepted. The guide's examples cover creating a Spark cluster, submitting a job to it, adding an autoscaling policy, listing clusters in a project and region, checking a cluster's status and deleting a cluster, then polling the long-running operation until it finishes. Read-only tools are flagged as such in their tool metadata.
Capabilities
- Create and delete Spark clusters
- Submit jobs to a cluster
- Create autoscaling policies
- List clusters and check cluster status
About
- Publisher
- Tool
- Google Cloud
Works with
Install
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
Details
| Fact | Value | Source |
|---|---|---|
| Type | MCP server | |
| Tool | Google Cloud | |
| Publisher | source | |
| Official status | Officiallisted on Google's own supported-products page for Google and Google Cloud MCP servers | source |
| Connection | Remote (hosted, you connect over the internet) | source |
| Can change data | Yes | source |
| Needs an API key or sign-in | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | ChatGPT | source |
| Licence | Not stated in its documentation | |
| Pricing | Not stated in its documentation | |
| Activity | No commit dataDownload data not available (not on npm or PyPI) | |
| Links | Website |